Abstract: Re-Identification of physical objects in an image background is made possible by the use of temporary data objects (i.e., video cookies). Image data including an image object representing a physical object in at least one of a plurality of backgrounds is pre-stored in a database. Identification data for the image object and image background data is extracted from the image object and a comparison is made to determine if the identification data matches identification data in the database. In the event no match is found, a temporary data object is created and stored in the database that links the identification data and the image background data. If an identification data match is found, it is determined whether a temporary data object exists in the database. If no temporary data object exists, one is created and stored in the database. If a temporary data object is determined to exist in the database, it is determined whether the temporary data object fulfills a predetermined condition(s).

Abstract: The invention refers to a computer-implemented method of analyzing video data to identify affiliates of an object of interest, the method comprising: identifying a plurality of occurrences of the object of interest in the video data; determining a set of potential affiliates for the object of interest from a plurality of other objects in the video data based on a criterion of closeness between the object of interest at each occurrence and each other object; analyzing the set of potential affiliates to obtain a similarity score for each potential affiliate at each occurrence from the plurality of occurrences, each similarity score indicating a degree of similarity with respect to a selected reference potential affiliate in the set of potential affiliates; and identifying a potential affiliate as an affiliate of the object of interest based on the similarity scores.

Abstract: The invention refers to a computer-implemented method of analyzing security documents having visible information and at least one of infrared and ultraviolet detectable information, the method comprising the steps of: receiving visible-color data of a first set of pixels of a first region of the security document in a first image of the security document and feeding the visible-color data to a convolutional neural network, CNN; receiving infrared, IR, and/or ultraviolet, UV, data of a second and/or third set of pixels of a respective second and/or third region in a respective second and/or third image of the security document and feeding the IR and/or UV data to the CNN; analyzing the visible-color data of the first set of pixels using the CNN to extract characteristics of the security document from the visible information; and analyzing the IR and/or UV data of the second and/or third set of pixels using the CNN to extract characteristics of the security document from the IR and/or UV information.

Abstract: The invention provides a method for video surveillance in a video-surveillance system comprising the steps of capturing video images by a video camera observing an area of surveillance; wherein the capturing the video images comprises making objects in the area of surveillance irrecognizable or invisible in captured video images; receiving, by a processor, a predetermined signal; based on the received predetermined signal, generating a first control signal by the processor and transmitting the first control signal to the video camera; receiving the first control signal by the video camera; based on the received first control signal, stopping making objects in the area of surveillance irrecognizable or invisible in the captured video images.

Abstract: The invention provides a method for processing and analyzing forensic video data using a computer program, the method comprising the steps of recording the forensic video data; providing supplementary data related to the recorded video data, wherein the supplementary data may be provided from or input by a source external of the computer program, in particular a human, or wherein the supplementary data may be extracted from the forensic video data by the computer program in an initial analyzing step; analyzing the forensic video data by the computer program using the supplementary data; and displaying a part of the forensic video data, the displayed part being based on a result of the analyzing step.

Abstract: The present invention relates to a computer-implemented method of identifying a physical object, comprising the steps of providing image data comprising an image object representing a physical object, analyzing the image data to extract identification data for the image object, providing supplementary data associated with a particular physical object, and determining whether the image object corresponds to the particular physical object based on the identification data and supplementary data.

Abstract: The invention provides a method for video surveillance in a video-surveillance system comprising the steps of capturing video images by a video camera observing an area of surveillance; wherein the capturing the video images comprises making objects in the area of surveillance irrecognizable or invisible in captured video images; receiving, by a processor, a predetermined signal; based on the received predetermined signal, generating a first control signal by the processor and transmitting the first control signal to the video camera; receiving the first control signal by the video camera; based on the received first control signal, stopping making objects in the area of surveillance irrecognizable or invisible in the captured video images.